
When I was able to load CentosOS as a host OS, Was able to use RDMA, but it seems like the 4.3x branch of nodeNG is missing RDMA support? I enabled rdma and started the service, but gluster refuses to recognize that RDMA is available and always reports RDMA port as 0 and when I try to make a new drive with tcp,rdma transport options, it always fails.

Il giorno ven 26 apr 2019 alle ore 01:56 <michael@wanderingmad.com> ha scritto:
When I was able to load CentosOS as a host OS, Was able to use RDMA, but it seems like the 4.3x branch of nodeNG is missing RDMA support? I enabled rdma and started the service, but gluster refuses to recognize that RDMA is available and always reports RDMA port as 0 and when I try to make a new drive with tcp,rdma transport options, it always fails.
Sahina, any hint?
_______________________________________________ Users mailing list -- users@ovirt.org To unsubscribe send an email to users-leave@ovirt.org Privacy Statement: https://www.ovirt.org/site/privacy-policy/ oVirt Code of Conduct: https://www.ovirt.org/community/about/community-guidelines/ List Archives: https://lists.ovirt.org/archives/list/users@ovirt.org/message/E73V472TTQVOLI...
-- SANDRO BONAZZOLA MANAGER, SOFTWARE ENGINEERING, EMEA R&D RHV Red Hat EMEA <https://www.redhat.com/> sbonazzo@redhat.com <https://red.ht/sig>

On Tue, Apr 30, 2019 at 3:35 PM Sandro Bonazzola <sbonazzo@redhat.com> wrote:
Il giorno ven 26 apr 2019 alle ore 01:56 <michael@wanderingmad.com> ha scritto:
When I was able to load CentosOS as a host OS, Was able to use RDMA, but it seems like the 4.3x branch of nodeNG is missing RDMA support? I enabled rdma and started the service, but gluster refuses to recognize that RDMA is available and always reports RDMA port as 0 and when I try to make a new drive with tcp,rdma transport options, it always fails.
Sahina, any hint?
Adding Rafi. Any errors in glusterd logs?
_______________________________________________ Users mailing list -- users@ovirt.org To unsubscribe send an email to users-leave@ovirt.org Privacy Statement: https://www.ovirt.org/site/privacy-policy/ oVirt Code of Conduct: https://www.ovirt.org/community/about/community-guidelines/ List Archives: https://lists.ovirt.org/archives/list/users@ovirt.org/message/E73V472TTQVOLI...
--
SANDRO BONAZZOLA
MANAGER, SOFTWARE ENGINEERING, EMEA R&D RHV
Red Hat EMEA <https://www.redhat.com/>
sbonazzo@redhat.com <https://red.ht/sig>

this is what I see in the logs when I try to add RDMA: [2019-05-06 16:54:50.305297] I [MSGID: 106521] [glusterd-op-sm.c:2953:glusterd_op_set_volume] 0-management: changing transport-type for volume storage_ssd to tcp,rdma [2019-05-06 16:54:50.309122] W [MSGID: 101095] [xlator.c:180:xlator_volopt_dynload] 0-xlator: /usr/lib64/glusterfs/5.3/xlator/nfs/server.so: cannot open shared object file: No such file or directory [2019-05-06 16:54:50.321422] E [MSGID: 106068] [glusterd-volgen.c:1025:volgen_write_volfile] 0-management: failed to create volfile [2019-05-06 16:54:50.321463] E [glusterd-volgen.c:6556:glusterd_create_volfiles] 0-management: Could not generate gfproxy client volfiles [2019-05-06 16:54:50.321476] E [MSGID: 106068] [glusterd-op-sm.c:3062:glusterd_op_set_volume] 0-management: Unable to create volfile for 'volume set' [2019-05-06 16:54:50.321488] E [MSGID: 106122] [glusterd-syncop.c:1434:gd_commit_op_phase] 0-management: Commit of operation 'Volume Set' failed on localhost [2019-05-06 16:54:50.323610] E [MSGID: 101191] [event-epoll.c:671:event_dispatch_epoll_worker] 0-epoll: Failed to dispatch handler rmda status: root@Prometheus glusterfs]# systemctl status rdma ● rdma.service - Initialize the iWARP/InfiniBand/RDMA stack in the kernel Loaded: loaded (/usr/lib/systemd/system/rdma.service; enabled; vendor preset: disabled) Active: active (exited) since Sun 2019-04-21 23:53:42 EDT; 2 weeks 0 days ago Docs: file:/etc/rdma/rdma.conf Main PID: 4968 (code=exited, status=0/SUCCESS) Tasks: 0 CGroup: /system.slice/rdma.service volume status: Gluster process TCP Port RDMA Port Online Pid ------------------------------------------------------------------------------ Brick 10.100.50.12:/gluster_bricks/storage_ nvme2/storage_nvme2 49153 0 Y 26888 Brick 10.100.50.14:/gluster_bricks/storage_ nvme2/storage_nvme2 49153 0 Y 3827 Brick 10.100.50.16:/gluster_bricks/storage_ nvme2/storage_nvme2 49153 0 Y 24238 Self-heal Daemon on localhost N/A N/A Y 29452 Self-heal Daemon on 10.100.50.16 N/A N/A Y 11058 Self-heal Daemon on 10.100.50.14 N/A N/A Y 8573

Rafi, can you take a look? On Mon, May 6, 2019 at 10:29 PM <michael@wanderingmad.com> wrote:
this is what I see in the logs when I try to add RDMA:
[2019-05-06 16:54:50.305297] I [MSGID: 106521] [glusterd-op-sm.c:2953:glusterd_op_set_volume] 0-management: changing transport-type for volume storage_ssd to tcp,rdma [2019-05-06 16:54:50.309122] W [MSGID: 101095] [xlator.c:180:xlator_volopt_dynload] 0-xlator: /usr/lib64/glusterfs/5.3/xlator/nfs/server.so: cannot open shared object file: No such file or directory [2019-05-06 16:54:50.321422] E [MSGID: 106068] [glusterd-volgen.c:1025:volgen_write_volfile] 0-management: failed to create volfile [2019-05-06 16:54:50.321463] E [glusterd-volgen.c:6556:glusterd_create_volfiles] 0-management: Could not generate gfproxy client volfiles [2019-05-06 16:54:50.321476] E [MSGID: 106068] [glusterd-op-sm.c:3062:glusterd_op_set_volume] 0-management: Unable to create volfile for 'volume set' [2019-05-06 16:54:50.321488] E [MSGID: 106122] [glusterd-syncop.c:1434:gd_commit_op_phase] 0-management: Commit of operation 'Volume Set' failed on localhost [2019-05-06 16:54:50.323610] E [MSGID: 101191] [event-epoll.c:671:event_dispatch_epoll_worker] 0-epoll: Failed to dispatch handler
rmda status: root@Prometheus glusterfs]# systemctl status rdma ● rdma.service - Initialize the iWARP/InfiniBand/RDMA stack in the kernel Loaded: loaded (/usr/lib/systemd/system/rdma.service; enabled; vendor preset: disabled) Active: active (exited) since Sun 2019-04-21 23:53:42 EDT; 2 weeks 0 days ago Docs: file:/etc/rdma/rdma.conf Main PID: 4968 (code=exited, status=0/SUCCESS) Tasks: 0 CGroup: /system.slice/rdma.service
volume status:
Gluster process TCP Port RDMA Port Online Pid ------------------------------------------------------------------------------ Brick 10.100.50.12:/gluster_bricks/storage_ nvme2/storage_nvme2 49153 0 Y 26888 Brick 10.100.50.14:/gluster_bricks/storage_ nvme2/storage_nvme2 49153 0 Y 3827 Brick 10.100.50.16:/gluster_bricks/storage_ nvme2/storage_nvme2 49153 0 Y 24238 Self-heal Daemon on localhost N/A N/A Y 29452 Self-heal Daemon on 10.100.50.16 N/A N/A Y 11058 Self-heal Daemon on 10.100.50.14 N/A N/A Y 8573
_______________________________________________ Users mailing list -- users@ovirt.org To unsubscribe send an email to users-leave@ovirt.org Privacy Statement: https://www.ovirt.org/site/privacy-policy/ oVirt Code of Conduct: https://www.ovirt.org/community/about/community-guidelines/ List Archives: https://lists.ovirt.org/archives/list/users@ovirt.org/message/4JZJXH3OFH3RPI...

On 5/7/19 8:44 PM, Sahina Bose wrote:
Rafi, can you take a look?
On Mon, May 6, 2019 at 10:29 PM <michael@wanderingmad.com> wrote:
this is what I see in the logs when I try to add RDMA:
Are you trying to change the transport type of the volume. If so, Have you followed the document [1] ? [1] : https://docs.gluster.org/en/latest/Administrator%20Guide/RDMA%20Transport/
[2019-05-06 16:54:50.305297] I [MSGID: 106521] [glusterd-op-sm.c:2953:glusterd_op_set_volume] 0-management: changing transport-type for volume storage_ssd to tcp,rdma [2019-05-06 16:54:50.309122] W [MSGID: 101095] [xlator.c:180:xlator_volopt_dynload] 0-xlator: /usr/lib64/glusterfs/5.3/xlator/nfs/server.so: cannot open shared object file: No such file or directory [2019-05-06 16:54:50.321422] E [MSGID: 106068] [glusterd-volgen.c:1025:volgen_write_volfile] 0-management: failed to create volfile [2019-05-06 16:54:50.321463] E [glusterd-volgen.c:6556:glusterd_create_volfiles] 0-management: Could not generate gfproxy client volfiles [2019-05-06 16:54:50.321476] E [MSGID: 106068] [glusterd-op-sm.c:3062:glusterd_op_set_volume] 0-management: Unable to create volfile for 'volume set' [2019-05-06 16:54:50.321488] E [MSGID: 106122] [glusterd-syncop.c:1434:gd_commit_op_phase] 0-management: Commit of operation 'Volume Set' failed on localhost [2019-05-06 16:54:50.323610] E [MSGID: 101191] [event-epoll.c:671:event_dispatch_epoll_worker] 0-epoll: Failed to dispatch handler
rmda status: root@Prometheus glusterfs]# systemctl status rdma ● rdma.service - Initialize the iWARP/InfiniBand/RDMA stack in the kernel Loaded: loaded (/usr/lib/systemd/system/rdma.service; enabled; vendor preset: disabled) Active: active (exited) since Sun 2019-04-21 23:53:42 EDT; 2 weeks 0 days ago Docs: file:/etc/rdma/rdma.conf Main PID: 4968 (code=exited, status=0/SUCCESS) Tasks: 0 CGroup: /system.slice/rdma.service
volume status:
Gluster process TCP Port RDMA Port Online Pid ------------------------------------------------------------------------------ Brick 10.100.50.12:/gluster_bricks/storage_ nvme2/storage_nvme2 49153 0 Y 26888 Brick 10.100.50.14:/gluster_bricks/storage_ nvme2/storage_nvme2 49153 0 Y 3827 Brick 10.100.50.16:/gluster_bricks/storage_ nvme2/storage_nvme2 49153 0 Y 24238 Self-heal Daemon on localhost N/A N/A Y 29452 Self-heal Daemon on 10.100.50.16 N/A N/A Y 11058 Self-heal Daemon on 10.100.50.14 N/A N/A Y 8573
_______________________________________________ Users mailing list -- users@ovirt.org To unsubscribe send an email to users-leave@ovirt.org Privacy Statement: https://www.ovirt.org/site/privacy-policy/ oVirt Code of Conduct: https://www.ovirt.org/community/about/community-guidelines/ List Archives: https://lists.ovirt.org/archives/list/users@ovirt.org/message/4JZJXH3OFH3RPI...

Tried that, get this error: [root@Icarus ~]# gluster volume stop storage_ssd Stopping volume will make its data inaccessible. Do you want to continue? (y/n) y volume stop: storage_ssd: success [root@Icarus ~]# gluster volume set storage_ssd config.transport tcp,rdma volume set: failed: Commit failed on localhost. Please check the log file for more details. and here is the glusterd.log [2019-05-09 21:10:45.945855] W [MSGID: 101095] [xlator.c:456:xlator_dynload] 0-xlator: /usr/lib64/glusterfs/5.3/xlator/nfs/server.so: cannot open shared object file: No such file or directory [2019-05-09 21:10:46.041341] I [MSGID: 106521] [glusterd-op-sm.c:2953:glusterd_op_set_volume] 0-management: changing transport-type for volume storage_ssd to tcp,rdma [2019-05-09 21:10:46.041965] W [MSGID: 101095] [xlator.c:180:xlator_volopt_dynload] 0-xlator: /usr/lib64/glusterfs/5.3/xlator/nfs/server.so: cannot open shared object file: No such file or di rectory [2019-05-09 21:10:46.059356] E [MSGID: 106068] [glusterd-volgen.c:1025:volgen_write_volfile] 0-management: failed to create volfile [2019-05-09 21:10:46.059394] E [glusterd-volgen.c:6556:glusterd_create_volfiles] 0-management: Could not generate gfproxy client volfiles [2019-05-09 21:10:46.059406] E [MSGID: 106068] [glusterd-op-sm.c:3062:glusterd_op_set_volume] 0-management: Unable to create volfile for 'volume set' [2019-05-09 21:10:46.059420] E [MSGID: 106122] [glusterd-syncop.c:1434:gd_commit_op_phase] 0-management: Commit of operation 'Volume Set' failed on localhost [2019-05-09 21:10:46.062304] E [MSGID: 101191] [event-epoll.c:671:event_dispatch_epoll_worker] 0-epoll: Failed to dispatch handler [root@prometheus ~]#
participants (4)
-
michael@wanderingmad.com
-
RAFI KC
-
Sahina Bose
-
Sandro Bonazzola